{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O4E6ARILPMYLKYLXX56BJY3FYA","short_pith_number":"pith:O4E6ARIL","canonical_record":{"source":{"id":"2203.00822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T02:18:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86ccb9d016c182b4eaa9501b5b638af8914072443415fbcf8fad4ae11f0a5341","abstract_canon_sha256":"fcd06ca599793781ac7ea243042557234359ce959da59249fe83d1b642c9c343"},"schema_version":"1.0"},"canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","source":{"kind":"arxiv","id":"2203.00822","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00822","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00822v1","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00822","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"O4E6ARILPMYL","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"pith_short_16","alias_value":"O4E6ARILPMYLKYLX","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"pith_short_8","alias_value":"O4E6ARIL","created_at":"2026-07-05T04:01:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O4E6ARILPMYLKYLXX56BJY3FYA","target":"record","payload":{"canonical_record":{"source":{"id":"2203.00822","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T02:18:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"86ccb9d016c182b4eaa9501b5b638af8914072443415fbcf8fad4ae11f0a5341","abstract_canon_sha256":"fcd06ca599793781ac7ea243042557234359ce959da59249fe83d1b642c9c343"},"schema_version":"1.0"},"canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:23.866042Z","signature_b64":"INQPhg1ajRLm4MsDD+YVIsZjTYPQ2XQSDelHBMhzX+/cp7nPNS4ODXGf8IRSqjff1Av0d/ZbdL57/9ta+5KxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","last_reissued_at":"2026-07-05T04:01:23.865501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:23.865501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.00822","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:01:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lnEEypp1n5Z7Wn492rvRt6XG+7iEHXBhLAkPhzWR0iNF11TzE9/06sqCvXRHqdUcGF4qXLBusWUTwG07bjiuDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:27:57.259028Z"},"content_sha256":"1882a5c54b877820426e5998d8882a49780bae47cc9ea207bb12d47e814b86ae","schema_version":"1.0","event_id":"sha256:1882a5c54b877820426e5998d8882a49780bae47cc9ea207bb12d47e814b86ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O4E6ARILPMYLKYLXX56BJY3FYA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Shangdong Yang, Shuyang Liu, Wenbin Li, Xiao Liu, Yang Gao","submitted_at":"2022-03-02T02:18:48Z","abstract_excerpt":"Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies. To address this problem, we propose Boundary Characterization via the Minimum Experience Retention (BCMER), an end-to-end Interpretable Policy Distillation (IPD) framework. Unlike previous IPD approaches, BCMER distinguishes the importance of experiences and keeps a minimal but critical experience pool with almost no loss of policy similarity. Specifically, the proposed BCMER contains two basic steps. Fir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00822","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2203.00822/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:01:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"feWDwHqf8RJS+hfr1yKUJT7hVg6E4UZbGcKIHgbv3ePC3BgDY8OQKo9SZpiFoAoFUFqwG1CXrCc/ugMCv0ogBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T08:27:57.259439Z"},"content_sha256":"34ed23462b3c3cd595c8935c462eeb7e00591701b2ee8c195097d8e790dbfe4f","schema_version":"1.0","event_id":"sha256:34ed23462b3c3cd595c8935c462eeb7e00591701b2ee8c195097d8e790dbfe4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/bundle.json","state_url":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O4E6ARILPMYLKYLXX56BJY3FYA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-14T08:27:57Z","links":{"resolver":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA","bundle":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/bundle.json","state":"https://pith.science/pith/O4E6ARILPMYLKYLXX56BJY3FYA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O4E6ARILPMYLKYLXX56BJY3FYA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O4E6ARILPMYLKYLXX56BJY3FYA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fcd06ca599793781ac7ea243042557234359ce959da59249fe83d1b642c9c343","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T02:18:48Z","title_canon_sha256":"86ccb9d016c182b4eaa9501b5b638af8914072443415fbcf8fad4ae11f0a5341"},"schema_version":"1.0","source":{"id":"2203.00822","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00822","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00822v1","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00822","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"pith_short_12","alias_value":"O4E6ARILPMYL","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"pith_short_16","alias_value":"O4E6ARILPMYLKYLX","created_at":"2026-07-05T04:01:23Z"},{"alias_kind":"pith_short_8","alias_value":"O4E6ARIL","created_at":"2026-07-05T04:01:23Z"}],"graph_snapshots":[{"event_id":"sha256:34ed23462b3c3cd595c8935c462eeb7e00591701b2ee8c195097d8e790dbfe4f","target":"graph","created_at":"2026-07-05T04:01:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2203.00822/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Although deep reinforcement learning has become a universal solution for complex control tasks, its real-world applicability is still limited because lacking security guarantees for policies. To address this problem, we propose Boundary Characterization via the Minimum Experience Retention (BCMER), an end-to-end Interpretable Policy Distillation (IPD) framework. Unlike previous IPD approaches, BCMER distinguishes the importance of experiences and keeps a minimal but critical experience pool with almost no loss of policy similarity. Specifically, the proposed BCMER contains two basic steps. Fir","authors_text":"Shangdong Yang, Shuyang Liu, Wenbin Li, Xiao Liu, Yang Gao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T02:18:48Z","title":"Keeping Minimal Experience to Achieve Efficient Interpretable Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00822","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1882a5c54b877820426e5998d8882a49780bae47cc9ea207bb12d47e814b86ae","target":"record","created_at":"2026-07-05T04:01:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fcd06ca599793781ac7ea243042557234359ce959da59249fe83d1b642c9c343","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-02T02:18:48Z","title_canon_sha256":"86ccb9d016c182b4eaa9501b5b638af8914072443415fbcf8fad4ae11f0a5341"},"schema_version":"1.0","source":{"id":"2203.00822","kind":"arxiv","version":1}},"canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7709e0450b7b30b56177bf7c14e365c034caadde811e53155899e91bcb76173c","first_computed_at":"2026-07-05T04:01:23.865501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:23.865501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"INQPhg1ajRLm4MsDD+YVIsZjTYPQ2XQSDelHBMhzX+/cp7nPNS4ODXGf8IRSqjff1Av0d/ZbdL57/9ta+5KxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:23.866042Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.00822","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1882a5c54b877820426e5998d8882a49780bae47cc9ea207bb12d47e814b86ae","sha256:34ed23462b3c3cd595c8935c462eeb7e00591701b2ee8c195097d8e790dbfe4f"],"state_sha256":"30df3ee1cd5b684b4aa4ea4a0cd3239ef25ce812b518842db63a788e2790ce4d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nM1n5Vzrv9taoAHXwvrx/yp0kUfLPX0l0epI6tv3tLPOC31whSJo6mHjz24FE64ftdGJkXsdpCCDQDu801HbCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T08:27:57.263048Z","bundle_sha256":"c81f7c4a53a8b7ec857cd508d325c78e1910789833cb0a2aea3d7dfd97f3f44d"}}